Jump to content
  • Advertisement


  • Content Count

  • Joined

  • Last visited

Community Reputation

6 Neutral

About Melodrive

  • Rank

Personal Information


  • Twitter

Recent Profile Visitors

The recent visitors block is disabled and is not being shown to other users.

  1. Hi Everyone! After being in private alpha for a few months, we've now released our AI music engine on the Unity Asset Store in open Beta as a Unity plugin. Melodrive is an engine that generates an infinite music stream that can adapt to the unique and complex requirements of a video game. We use state of the art synthesisers and samplers, along with pro-level effects and mixing to render the score generated by the AI. Melodrive comes with full Unity support out of the box, and is easily extendable to any other platform or technology with the native dynamic library. Developers and end-users can create their own music, by changing style and emotion, melody and instruments, in an instant, on the fly. Please note that this version of Melodrive is geared towards developers with little to no musical skills. We'd love to improve the engine and add features in order to extend the capabilities of professional musicians, but this will come at a later time! Here's a short trailer that gives you an idea of what you can do with Melodrive: You can download Melodrive Lite Beta for free from the Unity Asset Store at https://assetstore.unity.com/packages/audio/music/melodrive-lite-beta-129271 We'd love to get feedback and suggestions to improve our music engine. For this, you can join our Discord: https://discord.gg/ZGvF9NX Thanks!
  2. Many thanks for the nice words! As for the melodies, as well as for all the other musical elements, they are all generated algorithmically from scratch in realtime. We don't use any pre-composed midi melodies.
  3. Melodrive

    The Total Beginner's Guide to Game AI

    Nice insight, thanks! Unfortunately, I know way to well what it means not to have a fitness function you can rely on for reinforcement learning My work/research is focused on developing AI systems which generate music. It's quite challenging to find suitable fitness functions which may measure the "goodness" of the generated music, in order to evaluate a generative model. Reinforcement learning - also beyond NNs - is still not really an option in generative music. On the bright side, I was playing around with deep reinforcement learning in artificial society/life simulations. There, I found the application of RL to be really interesting. With RL, the single agents of a society can evolve very complex behaviours, sometimes unpredictable, without hard-coded instructions. With the "right" reward system, you can end up having emergent behaviour at the level of the super-system. As someone who's really passionate about complexity science, I'm excited to see the (unexplored) possibilities that this technique may open up in this field as well.
  4. Melodrive

    The Total Beginner's Guide to Game AI

    This is an amazing overview! I'd just like to comment on one point regarding the use of neural networks: The statement definitely rings true for supervised learning techniques usefdfor training neural nets. However, the late advancements in reinforcement learning could make the use of neural networks feasible also in commercial gaming. Differently from supervised learning, reinforcement learning enables developers to train a neural network without the need of training data. In a reinforcement learning setting, a network can learn by trial and error by running a number of simulations of a game and being exposed to a system of rewards. This approach has been proven to be very successful for developing AI agents that play Atari games, Go and Chess thanks to the work carried out at Deep Mind. Several techniques have been proposed to train networks with reinforcement learning, such as Q-Learning and the use of Genetic Algorithms as a way of evolving the weights and hyper-parameters of a training network. This is definitely exciting research that I'd love to see included in commercial games at some point!
  5. You can take a look at our demos at http://melodrive.com. There are also short video trailers on the website, so you don't need to download them. However, the demos are relatively simple use cases, so they don't really show the full range of possibilities of the system. (We kept them simple, as we already found that people outside of video game music has a difficult time grasping what we're doing!). "Oceania" and "SoundSlides", show the emotional change in the same style with same musical theme. With "WorldMusic", you can listen to the same musical theme passed through different styles. In "LightSynth" you can see how users may directly affect the emotional state of the music, always based on the same musical theme. Unfortunately, we don't have a demo that showcases multiple musical themes.
  6. Hey nsmadsen, thanks for the thoughtful feedback! We're actually addressing the issue of coherence and self-reference throughout a soundtrack. I very well know that so far most of the generative music systems lack on that point. To address that, all the music that Melodrive generates is built around the idea of a musical theme. A musical theme can be implemented into a number of different styles/emotions (in realtime) and attached to game objects and locations. Moving forward, we'll also try to implement concurrent musical themes in the same musical setting, if say for example, the boss and the protagonist, with their unique themes, are both in the same scene. Apart from being AI researchers, we all have a strong musical background and are trying to have our AI "think" as an opera/video game composer would think. We definitely don't want to replace composers, rather we would love to arrive at a point where the composers can direct the AI in order to create highly adaptive music which is not possible today, given the obvious limited resources of a composer. We call this deep adaptive music. With deep adaptive music, human composers/devs can provide the core musical ideas to the AI, which then implements these in realtime in order to fit the non-linear experience at any time. Hope this clarifies our approach
  7. Over the last 1.5yrs, I've worked with my colleagues on Melodrive, an AI music engine that enables people with limited to no musical skills to easily create highly adaptive music. The music engine uses AI to generate music from scratch, in realtime. The music smoothly transitions between different emotional states. We're planning on releasing the engine for free to indies. This means that indies can quickly get a soundtrack, which is more dynamic than anything that exists today on the market - composers included! We’ve just released four Melodrive tech demos. These showcase Melodrive's AI music potential across a range of experiences from VR to music branding. You can download the demos directly from our website here: http://melodrive.com You can also sign up to become an alpha tester. Hope this may be of interest to you!
  • Advertisement

Important Information

By using GameDev.net, you agree to our community Guidelines, Terms of Use, and Privacy Policy.

GameDev.net is your game development community. Create an account for your GameDev Portfolio and participate in the largest developer community in the games industry.

Sign me up!